4 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 4 / 4
Yayın Software defect prediction using Bayesian networks(Springer, 2014-02) Okutan, Ahmet; Yıldız, Olcay TanerThere are lots of different software metrics discovered and used for defect prediction in the literature. Instead of dealing with so many metrics, it would be practical and easy if we could determine the set of metrics that are most important and focus on them more to predict defectiveness. We use Bayesian networks to determine the probabilistic influential relationships among software metrics and defect proneness. In addition to the metrics used in Promise data repository, we define two more metrics, i.e. NOD for the number of developers and LOCQ for the source code quality. We extract these metrics by inspecting the source code repositories of the selected Promise data repository data sets. At the end of our modeling, we learn the marginal defect proneness probability of the whole software system, the set of most effective metrics, and the influential relationships among metrics and defectiveness. Our experiments on nine open source Promise data repository data sets show that response for class (RFC), lines of code (LOC), and lack of coding quality (LOCQ) are the most effective metrics whereas coupling between objects (CBO), weighted method per class (WMC), and lack of cohesion of methods (LCOM) are less effective metrics on defect proneness. Furthermore, number of children (NOC) and depth of inheritance tree (DIT) have very limited effect and are untrustworthy. On the other hand, based on the experiments on Poi, Tomcat, and Xalan data sets, we observe that there is a positive correlation between the number of developers (NOD) and the level of defectiveness. However, further investigation involving a greater number of projects is needed to confirm our findings.Yayın A novel kernel to predict software defectiveness(Elsevier Science Inc, 2016-09) Okutan, Ahmet; Yıldız, Olcay TanerAlthough the software defect prediction problem has been researched for a long time, the results achieved are not so bright. In this paper, we propose to use novel kernels for defect prediction that are based on the plagiarized source code, software clones and textual similarity. We generate precomputed kernel matrices and compare their performance on different data sets to model the relationship between source code similarity and defectiveness. Each value in a kernel matrix shows how much parallelism exists between the corresponding files of a software system chosen. Our experiments on 10 real world datasets indicate that support vector machines (SVM) with a precomputed kernel matrix performs better than the SVM with the usual linear kernel in terms of F-measure. Similarly, when used with a precomputed kernel, the k-nearest neighbor classifier (KNN) achieves comparable performance with respect to KNN classifier. The results from this preliminary study indicate that source code similarity can be used to predict defect proneness.Yayın Psychometric properties of the Turkish version of the eating pathology symptoms inventory (EPSI-T)(Cogent OA, 2025) Türk, Fidan; Acet, Pınar; Karabulut, Goncagül; Akay, NazlıThe purpose of this study was to examine the factor structure and psychometric properties of the Turkish version of the Eating Pathology Symptoms Inventory (EPSI‑T), and to explore gender differences in eating disorder symptoms. Participants were 473 university students in Türkiye (342 women, 113 men) who completed the EPSI‑T, along with the Modified Weight Bias Internalization Scale (WBIS‑M), Addiction‑like Eating Behaviour Scale (AEBS), Muscularity‑Oriented Eating Test (MOET), and Depression Anxiety and Stress Scales (DASS‑21). Confirmatory factor analysis supported the original eight‑factor, 45‑item structure [χ2(914) = 1994.57, χ2/df = 2.18, CFI = 0.90, RMSEA = 0.05 (0.05–0.06), SRMR = 0.07]. Women scored significantly higher on most subscales, except for Excessive Exercise, Muscle Building, and Negative Attitudes toward Obesity, where men scored higher (p < 0.005). Reliability was strong, with Cronbach’s α ranging from 0.72 to 0.90 and McDonald’s ω from 0.75 to 0.90. Convergent and discriminant validity were also supported. Overall, findings suggest that the EPSI‑T is a reliable and valid measure of eating disorder symptoms in Turkish‑speaking populations and may facilitate cross‑cultural research by providing a tool structurally consistent with the original English version.Yayın Reliability of direct-to-home teleneuropsychological assessment: a within-subject design study(Routledge, 2025-07-04) Yıldırım, Elif; Soncu Büyükişcan, Ezgi; Akça Kalem, Şükriye; Gürvit, HakanObjective: During the COVID-19 pandemic, the need to continue diagnosis and treatment processes, in addition to scientific research, led to a rapid shift towards direct-to-home tele-neuropsychology administrations, the reliability and validity of which had not been clearly established then. This study, therefore, aimed to examine the reliability of direct-to-home tele-neuropsychological assessment (TNP). Method: The sample included 105 cognitively healthy individuals aged between 50–83 years, and 47 patients diagnosed with neurocognitive disorders (mild cognitive impairment and early-stage Alzheimer’s type dementia). All participants underwent both face-to-face and teleneuropsychological assessments in a counterbalanced order. Results: The results revealed that performances across measures of attention, working memory, verbal fluency, verbal and visual memory, and visual perception were comparable across assessment modalities. Intraclass correlation coefficients of the tests ranged from.54 to.92. Conclusions: The findings of the study provide support for direct-to-home teleneuropsychological assessment among patients with neurocognitive disorders. Neuropsychological tests relying on verbal administration and independent of motor performance may represent a reliable alternative for this patient group when administered in settings where external distractions or technological limitations are controlled. For cognitively healthy individuals, on the other hand, the reliability of the TNP application is more questionable for memory and some executive function tests and therefore needs further exploration.
